TY - JOUR
T1 - Cognitive Impairment Classification Prediction Model Using Voice Signal Analysis
AU - Sung, Sang Ha
AU - Hong, Soongoo
AU - Kim, Jong Min
AU - Kang, Do Young
AU - Park, Hyuntae
AU - Kim, Sangjin
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/9
Y1 - 2024/9
N2 - As the population ages, Alzheimer’s disease (AD) and Parkinson’s disease (PD) are increasingly common neurodegenerative diseases among the elderly. Human voice signals contain various characteristics, and the voice recording signals with time-series properties include key information such as pitch, tremor, and breathing cycle. Therefore, this study aims to propose an algorithm to classify normal individuals, Alzheimer’s patients, and Parkinson’s patients using these voice signal characteristics. The study subjects consist of a total of 700 individuals, who provided data by uttering 40 predetermined sentences. To extract the main characteristics of the recorded voices, a Mel–spectrogram was used, and these features were analyzed using a Convolutional Neural Network (CNN). The analysis results showed that the classification based on DenseNet exhibited the best performance. This study suggests the potential for classification of cognitive impairment through voice signal analysis.
AB - As the population ages, Alzheimer’s disease (AD) and Parkinson’s disease (PD) are increasingly common neurodegenerative diseases among the elderly. Human voice signals contain various characteristics, and the voice recording signals with time-series properties include key information such as pitch, tremor, and breathing cycle. Therefore, this study aims to propose an algorithm to classify normal individuals, Alzheimer’s patients, and Parkinson’s patients using these voice signal characteristics. The study subjects consist of a total of 700 individuals, who provided data by uttering 40 predetermined sentences. To extract the main characteristics of the recorded voices, a Mel–spectrogram was used, and these features were analyzed using a Convolutional Neural Network (CNN). The analysis results showed that the classification based on DenseNet exhibited the best performance. This study suggests the potential for classification of cognitive impairment through voice signal analysis.
KW - Alzheimer’s disease (AD)
KW - Parkinson’s disease (PD)
KW - classification
KW - convolutional neural network (CNN)
KW - voice data
UR - http://www.scopus.com/inward/record.url?scp=85205079762&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85205079762&partnerID=8YFLogxK
U2 - 10.3390/electronics13183644
DO - 10.3390/electronics13183644
M3 - Article
AN - SCOPUS:85205079762
SN - 2079-9292
VL - 13
JO - Electronics (Switzerland)
JF - Electronics (Switzerland)
IS - 18
M1 - 3644
ER -